Safety production regulation and control method and system based on AI

Abstract

The invention provides a safety production regulation and control method and system based on AI. The method comprises the steps that pressure data of a wellhead and a pipeline are collected in real time through a pressure sensor, and the pressure of the wellhead and the pipeline is adjusted according to the deviation value between the pressure data of the wellhead and the pipeline and production requirement indexes; when the deviation value between the pressure data of the wellhead and the pipeline and the production requirement index still cannot meet the preset deviation requirement, safety early warning is conducted; vibration operation parameters of each piece of production equipment are collected in real time through a sensor set, and safety regulation and control are conducted on equipment operation according to the vibration operation parameters of each piece of production equipment; and when the vibration operation of each piece of production equipment still cannot meet the corresponding vibration operation standard, carrying out safety early warning on the production equipment of which the vibration operation still cannot meet the corresponding vibration operation standard. The system comprises modules corresponding to the steps of the method.

Description

Technical Field

[0001] The present invention proposes an AI-based safe production control method and system, which belongs to the technical field of safe production monitoring. Background Art

[0002] Oil extraction is a complex and high-risk industry. Its production process involves many links and equipment. Any mistake in any link may lead to safety accidents. Traditional oil extraction safety production control methods mainly rely on manual monitoring and simple sensor monitoring. These methods have many limitations and cannot meet the current high requirements of oil extraction industry for safety production. Existing wellhead and pipeline pressure control methods mainly rely on data collected by pressure sensors, but they can only achieve simple pressure adjustment and cannot accurately control according to production requirements. When the deviation between pressure data and production requirements exceeds the preset range, the existing technology can only perform simple alarms and lack intelligent early warning and control mechanisms. At the same time, the existing production equipment vibration operation parameter monitoring method mainly relies on data collected by vibration sensors, but it can only achieve data collection and storage, and cannot perform real-time analysis and early warning of the equipment's operating status. When the vibration operation parameters of the equipment exceed the standard range, the existing technology can only perform post-processing and cannot perform safety early warning and control in advance.

[0003] In view of the limitations of traditional safety production control methods and existing technologies, this paper proposes an AI-based safety production control method for oil production. This method introduces artificial intelligence technology to achieve real-time collection, intelligent analysis and precise control of key data such as wellhead and pipeline pressure, production equipment vibration operating parameters, etc. Summary of the invention

[0004] The present invention provides an AI-based safe production control method and system to solve the technical problems existing in the above-mentioned prior art. The technical solutions adopted are as follows: A safety production control method based on AI, the safety production control method based on AI comprising: The pressure sensor collects the pressure data of the wellhead and pipeline in real time, and adjusts the pressure of the wellhead and pipeline according to the deviation between the pressure data of the wellhead and pipeline and the production requirement index; After the pressure of the wellhead and pipeline is regulated, if the deviation between the pressure data of the wellhead and pipeline and the production requirement index still cannot meet the preset deviation requirement, a safety warning will be issued; The vibration operating parameters of each production equipment are collected in real time through the sensor group, and the operation of the equipment is safely regulated according to the vibration operating parameters of each production equipment; When each production equipment completes safety regulation, if the vibration operation of each production equipment still cannot meet its corresponding vibration operation standard, a safety warning is issued for the production equipment whose vibration operation still cannot meet its corresponding vibration operation standard.

[0005] Furthermore, the pressure data of the wellhead and pipeline are collected in real time through the pressure sensor, and the pressure of the wellhead and pipeline is adjusted according to the deviation between the pressure data of the wellhead and pipeline and the production requirement index, including: A first pressure sensor is installed at each of the multiple pressure monitoring positions at the wellhead; A second pressure sensor is installed at each of the multiple pressure detection node positions of the pipeline; Using the first pressure sensor to collect wellhead pressure data in real time, and regulating the wellhead pressure according to the deviation between the wellhead pressure data and the corresponding wellhead pressure production requirement index; The second pressure sensor is used to collect pipeline pressure data in real time, and the pipeline pressure is regulated according to the deviation between the pipeline pressure data and the corresponding pipeline pressure production requirement index.

[0006] Furthermore, the first pressure sensor is used to collect the pressure data of the wellhead in real time, and the pressure of the wellhead is regulated according to the deviation between the pressure data of the wellhead and the corresponding wellhead pressure production requirement index, including: Extracting the wellhead pressure data collected in real time by each of the first pressure sensors; Compare the deviation between the pressure data of each wellhead and its corresponding wellhead pressure production requirement index with a first pressure deviation threshold and a second pressure deviation threshold; When the deviation between the wellhead pressure data and the corresponding wellhead pressure production requirement index exceeds a preset first pressure deviation threshold, but does not exceed a second pressure deviation threshold, the historical pressure data collected by the first pressure sensor corresponding to the wellhead pressure data exceeding the preset first pressure deviation threshold is retrieved; Obtaining a pressure deviation evaluation coefficient using historical pressure data collected by a first pressure sensor corresponding to the wellhead pressure data exceeding a preset first pressure deviation threshold; comparing the pressure deviation evaluation coefficient with a preset pressure deviation evaluation threshold; When the pressure deviation evaluation coefficient exceeds the preset pressure deviation evaluation threshold, the pressure at the wellhead is regulated by increasing or reducing pressure according to the deviation between the pressure data at the wellhead exceeding the preset first pressure deviation threshold and the corresponding wellhead pressure production requirement index, so as to reduce the deviation between the pressure data at the wellhead and the corresponding wellhead pressure production requirement index; When the deviation between the wellhead pressure data and its corresponding wellhead pressure production requirement index exceeds a preset second pressure deviation threshold, the wellhead pressure is regulated by increasing or reducing the pressure according to the deviation between the wellhead pressure data exceeding the preset second pressure deviation threshold and its corresponding wellhead pressure production requirement index, so as to reduce the deviation between the wellhead pressure data and its corresponding wellhead pressure production requirement index.

[0007] Further, obtaining a pressure deviation evaluation coefficient using historical pressure data collected by a first pressure sensor corresponding to the wellhead pressure data exceeding a preset first pressure deviation threshold value includes: When the number of first pressure sensors corresponding to the pressure data of the wellhead exceeding the preset first pressure deviation threshold is one, the first pressure sensor corresponding to the pressure data of the wellhead exceeding the preset first pressure deviation threshold is used as a target pressure sensor, and the historical pressure data collected by the target pressure sensor is retrieved; The pressure deviation evaluation coefficient is obtained by using the first evaluation coefficient model in combination with the historical pressure data collected by the target pressure sensor; wherein the pressure deviation evaluation coefficient is obtained by the following formula: Among them, S 01 represents the pressure deviation evaluation coefficient obtained by the first evaluation coefficient model; a, b and c represent the preset first adjustment parameter, second adjustment parameter and third adjustment parameter respectively, and the value ranges of the first adjustment parameter, the second adjustment parameter and the third adjustment parameter are 0.58-1.13, 0.89-1.22 and 1.14-1.39; P b represents the pressure standard deviation corresponding to the historical pressure data collected by the target pressure sensor; n represents the number of pressure data of the historical pressure data; P i represents the pressure data value corresponding to the i-th historical pressure data; P i-1 represents the pressure data value corresponding to the i-1th historical pressure data; P be Indicates the preset force standard deviation reference value; P fmaxi represents the maximum value of the pressure change amplitude between two adjacent pressure data collection moments corresponding to the i-th historical pressure data; P fmini Indicates the minimum value of the pressure change amplitude between two adjacent pressure data collection moments corresponding to the i-th historical pressure data; When there are multiple first pressure sensors corresponding to the pressure data at the wellhead exceeding the preset first pressure deviation threshold, the first pressure sensor corresponding to the pressure data at the wellhead exceeding the preset first pressure deviation threshold is used as a target pressure sensor, and historical pressure data collected by the multiple target pressure sensors are retrieved; The pressure deviation evaluation coefficient is obtained by using the second evaluation coefficient model in combination with the historical pressure data collected by the plurality of target pressure sensors; wherein the pressure deviation evaluation coefficient is obtained by the following formula: Among them, S 02 represents the pressure deviation evaluation coefficient obtained by the second evaluation coefficient model; m represents the number of target pressure sensors; P bi represents the standard deviation of the pressure data corresponding to the historical pressure data of the i-th target pressure sensor; G i represents the average value of the correlation coefficient between the i-th target pressure sensor and other target pressure sensors; w i represents the weight value corresponding to the i-th target pressure sensor; P fmax01i represents the maximum pressure change amplitude corresponding to the i-th target pressure sensor; P fmax02i The maximum value of the pressure variation amplitude of the target pressure sensor corresponding to the maximum value of the correlation coefficient of the i-th target pressure sensor.

[0008] Furthermore, the second pressure sensor is used to collect the pressure data of the pipeline in real time, and the pressure of the pipeline is regulated according to the deviation between the pressure data of the pipeline and the corresponding pipeline pressure production requirement index, including: Retrieving pipeline pressure data collected by the second pressure sensor in real time; Compare the pressure data of each pipeline with its corresponding pressure risk threshold and pressure warning threshold; When the pressure data of the pipeline exceeds the corresponding pressure warning threshold, the pipeline valve corresponding to the pressure detection node position of the pipeline where the pressure data exceeds the corresponding pressure warning threshold is directly adjusted to reduce the pressure value corresponding to the pressure detection node position of the pipeline; When the pressure data of the pipeline exceeds its corresponding pressure risk threshold, the target pressure detection node position is screened out from the pressure detection node positions of all pipelines, and the target pressure data corresponding to the target pressure detection node position is used to obtain the pressure risk assessment coefficient, and the pressure control judgment of the pressure detection node position is performed using the pressure risk assessment coefficient.

[0009] Furthermore, when the pressure data of the pipeline exceeds its corresponding pressure risk threshold, a target pressure detection node position is screened out from the pressure detection node positions of all pipelines, and a pressure risk evaluation coefficient is obtained using the target pressure data corresponding to the target pressure detection node position, and a pressure control determination of the pressure detection node position is performed using the pressure risk evaluation coefficient, including: When the pressure data of the pipeline exceeds the corresponding pressure risk threshold, the correlation coefficient between the pressure detection node position of the pipeline whose pressure data exceeds the corresponding pressure risk threshold and the pressure detection node positions of other pipelines is retrieved; Retrieving the pressure detection node positions of the pipelines whose pressure data exceeds the corresponding pressure risk threshold and the pressure detection node positions of other pipelines whose correlation coefficients exceed the preset correlation coefficient threshold as the target pressure detection node positions, and taking the pressure data corresponding to the target pressure detection node positions as the target pressure data; Obtaining a pressure risk assessment coefficient using the pressure data of the pipeline corresponding to the pressure detection node position of the pipeline where the pressure data of the pipeline exceeds the corresponding pressure risk threshold and its corresponding target pressure data; The pressure risk assessment coefficient is obtained by the following formula: Where K represents the pressure risk assessment coefficient; k represents the number of target pressure detection node locations; P g The pressure data of the pipeline corresponding to the pressure detection node position of the pipeline where the pressure data of the pipeline exceeds the corresponding pressure risk threshold; P gi represents the target pressure data corresponding to the position of the i-th target pressure detection node; F i represents the correlation coefficient between the pressure detection node position of the pipeline whose pressure data exceeds its corresponding pressure risk threshold and the i-th target pressure detection node position; δ represents the preset time attenuation coefficient; t i represents the total pressure data collection time corresponding to the i-th target pressure detection node position; λ 01 and λ 02 represent the first risk factor and the second risk factor respectively, and the first risk factor is obtained by the following formula: Among them, λ 01 represents the first risk factor; F i The correlation coefficient between the pressure detection node position of the pipeline whose pressure data exceeds its corresponding pressure risk threshold and the i-th target pressure detection node position; F y Indicates the preset correlation coefficient threshold; Fmax Indicates the maximum value of the correlation coefficient between the pressure detection node positions of the pipeline corresponding to the n target pressure detection node positions and the pressure data of the pipeline exceeding the corresponding pressure risk threshold; Furthermore, the second risk factor is obtained by the following formula: Among them, λ 02 represents the second risk factor; P gb The standard deviation of the pressure data corresponding to the pressure detection node position of the pipeline where the pressure data of the pipeline exceeds the corresponding pressure risk threshold; P gbi represents the standard deviation of the pressure data corresponding to the position of the i-th target pressure detection node; F i The correlation coefficient between the pressure detection node position of the pipeline indicating that the pressure data of the pipeline exceeds the corresponding pressure risk threshold and the i-th target pressure detection node position; Comparing the stress risk assessment coefficient with a preset stress risk assessment threshold; When the pressure risk assessment coefficient exceeds the preset pressure risk assessment threshold, the pipeline valve corresponding to the pressure detection node position of the pipeline whose pressure data exceeds its corresponding pressure warning threshold is adjusted to reduce the pressure value corresponding to the pressure detection node position of the pipeline.

[0010] Furthermore, the vibration operating parameters of each production equipment are collected in real time by the sensor group, and the equipment operation is safely regulated according to the vibration operating parameters of each production equipment, including: The vibration operation parameters of each production equipment are collected in real time by a sensor group, wherein the sensor group includes an acceleration sensor, a velocity sensor and a displacement sensor, and the vibration operation parameters include vibration acceleration, vibration velocity and vibration displacement generated by vibration; The vibration acceleration, vibration velocity and vibration displacement generated by the vibration of each production equipment are compared with the corresponding acceleration threshold, velocity threshold and vibration displacement threshold respectively; When any one of the vibration acceleration, vibration velocity and vibration displacement generated by the vibration exceeds its corresponding threshold, it is determined whether the production equipment needs to be safely regulated; When it is determined that safety regulation of the production equipment is required, the production equipment is decelerated and regulated.

[0011] Furthermore, when any one of the vibration acceleration, vibration velocity and vibration displacement generated by the vibration exceeds its corresponding threshold, it is determined whether the production equipment needs to be safely regulated, including: When any one of the vibration acceleration, vibration velocity and vibration displacement generated by vibration exceeds its corresponding threshold value, the corresponding time when any one of the vibration acceleration, vibration velocity and vibration displacement generated by vibration exceeds its corresponding threshold value is used as the data retrieval time; From the moment of data retrieval, the vibration operation parameters of the production equipment are retrieved in real time; wherein the vibration operation parameters include vibration acceleration, vibration velocity and vibration displacement generated by vibration; Obtaining a vibration operation evaluation coefficient using the vibration operation parameters of the production equipment; The vibration operation evaluation coefficient is obtained by the following formula: Among them, U represents the vibration operation evaluation coefficient; A, V and D represent vibration acceleration, vibration velocity and vibration displacement caused by vibration respectively; RMS (A, V, D) represents the sum of the square root values ​​of vibration acceleration, vibration velocity and vibration displacement caused by vibration; MAD (A, V, D) represents the sum of the mean absolute deviation values ​​of vibration acceleration, vibration velocity and vibration displacement caused by vibration; STD (A, V, D) represents the sum of the standard deviations of vibration acceleration, vibration velocity and vibration displacement caused by vibration; Var (A, V, D) represents the sum of the variances of vibration acceleration, vibration velocity and vibration displacement caused by vibration; K b represents a preset basic adjustment coefficient, and the value range of the basic adjustment coefficient is 1.32-1.47; σ represents a preset scaling factor, and the value range of the scaling factor is 0.18-0.53; ε represents a preset minimum constant, which is used to prevent the denominator from being zero; comparing the vibration operation evaluation coefficient with a preset vibration operation evaluation coefficient threshold; When the vibration operation evaluation coefficient exceeds a preset vibration operation evaluation coefficient, it is determined that safety regulation of the production equipment is required.

[0012] Furthermore, when it is determined that the production equipment needs to be safely regulated, the production equipment is decelerated and regulated, including: When it is determined that production equipment needs to be safely regulated, the vibration operation evaluation coefficient is retrieved; The vibration operation evaluation coefficient is used to obtain a deceleration control ratio of the production equipment, and the production equipment is decelerated and controlled according to the deceleration control ratio of the production equipment; The deceleration control ratio of the production equipment is obtained by the following formula: Among them, B represents the deceleration control ratio of the production equipment; r represents the preset proportional adjustment coefficient, and the value range of the proportional adjustment coefficient is 0.27-0.34; U represents the vibration operation evaluation coefficient.

[0013] A safe production control system based on AI, the safe production control system based on AI comprising: the safe production control system based on AI comprising: The first adjustment module is used to collect the pressure data of the wellhead and the pipeline in real time through the pressure sensor, and adjust the pressure of the wellhead and the pipeline according to the deviation between the pressure data of the wellhead and the pipeline and the production requirement index; The first safety warning module is used to issue a safety warning when the deviation between the pressure data of the wellhead and the pipeline and the production requirement index still cannot meet the preset deviation requirement after the pressure of the wellhead and the pipeline is regulated; A second adjustment module is used to collect the vibration operation parameters of each production equipment in real time through a sensor group, and to safely regulate the operation of the equipment according to the vibration operation parameters of each production equipment; The second safety warning module is used to issue a safety warning to the production equipment whose vibration operation still cannot meet its corresponding vibration operation standard after each production equipment completes safety regulation.

[0014] Beneficial effects of the present invention: The AI-based production safety control method and system proposed in the present invention can timely discover and deal with potential safety hazards by real-time collection and analysis of the operating data of wellheads, pipelines and production equipment, thereby greatly reducing the probability of safety accidents. The AI ​​system can accurately control the pressure of the wellhead and pipeline according to the production requirement indicators to ensure the stability and continuity of the production process. At the same time, by real-time control of the vibration operating parameters of the production equipment, the equipment can be prevented from being shut down or damaged due to abnormal vibration, thereby improving the utilization rate and production efficiency of the equipment. Through intelligent production safety control methods, enterprises can reduce losses and downtime caused by safety accidents and equipment failures. At the same time, the application of AI systems can also help enterprises optimize resource allocation and reduce maintenance costs. The AI ​​system can provide key production data and analysis results in real time, providing a scientific basis for the company's decision-making. This helps companies quickly respond to market changes and changes in production demand, thereby formulating more reasonable production plans and strategies. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 is a flow chart of the method of the present invention; Figure 2 The system block diagram of the system of the present invention. DETAILED DESCRIPTION

[0016] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0017] The embodiment of the present invention proposes an AI-based safety production control method, such as Figure 1 As shown, the AI-based safe production control method includes: S1. The pressure data of the wellhead and pipeline are collected in real time through the pressure sensor, and the pressure of the wellhead and pipeline is adjusted according to the deviation between the pressure data of the wellhead and pipeline and the production requirement index; S2. After the pressure of the wellhead and pipeline is regulated, if the deviation between the pressure data of the wellhead and pipeline and the production requirement index still cannot meet the preset deviation requirement, a safety warning is issued; S3. Collecting the vibration operation parameters of each production equipment in real time through the sensor group, and safely regulating the operation of the equipment according to the vibration operation parameters of each production equipment; S4. After each production equipment completes safety regulation, if the vibration operation of each production equipment still cannot meet its corresponding vibration operation standard, a safety warning is issued for the production equipment whose vibration operation still cannot meet its corresponding vibration operation standard.

[0018] The working principle of the above technical solution is as follows: pressure sensors are deployed at the wellhead and pipeline to collect pressure data at these key locations in real time. The collected pressure data is input into the AI ​​system, and the system calculates the deviation between the pressure data and the production requirements according to the preset production requirements. According to the deviation, the AI ​​system adjusts the pressure of the wellhead and pipeline in real time by controlling valves, pumps and other regulating equipment to keep the pressure within a safe range. After completing the pressure regulation, the AI ​​system will check the deviation between the pressure data of the wellhead and pipeline and the production requirements again. If the deviation still cannot meet the preset deviation requirements (that is, it exceeds the safety range), the AI ​​system will trigger the safety warning mechanism, issue an alarm to the operator, and may automatically take further emergency measures. The sensor group is deployed on each production equipment to collect the vibration operating parameters of the equipment (such as amplitude, frequency, etc.) in real time. According to the preset vibration operating standards, the AI ​​system analyzes the vibration operating parameters of each equipment and determines whether the equipment is in normal operation. If it is found that the vibration operating parameters of the equipment exceed the standard range, the AI ​​system will control the equipment in real time by controlling the operating parameters of the equipment (such as speed, load, etc.) to keep the equipment in a safe operating state. After completing the equipment operation control, the AI ​​system will check again whether the vibration operation parameters of each device meet the corresponding vibration operation standards. If there are still devices whose vibration operation parameters cannot meet the standards (that is, the equipment is still in an abnormal state), the AI ​​system will trigger the safety warning mechanism, send an alarm to the operator, and may recommend shutdown for maintenance or take other necessary measures.

[0019] The effect of the above technical solution is: by real-time collection and analysis of the operating data of the wellhead, pipeline and production equipment, the AI ​​system can promptly discover and deal with potential safety hazards, thereby greatly reducing the probability of safety accidents. The AI ​​system can accurately control the pressure of the wellhead and pipeline according to the production requirements to ensure the stability and continuity of the production process. At the same time, by real-time control of the vibration operating parameters of the production equipment, the equipment can be prevented from being shut down or damaged due to abnormal vibration, thereby improving the utilization rate and production efficiency of the equipment. Through intelligent production safety control methods, enterprises can reduce losses and downtime caused by safety accidents and equipment failures. At the same time, the application of AI systems can also help enterprises optimize resource allocation and reduce maintenance costs. The AI ​​system can provide key production data and analysis results in real time, providing a scientific basis for the company's decision-making. This helps companies quickly respond to market changes and changes in production demand, thereby formulating more reasonable production plans and strategies.

[0020] In summary, this technical solution, through the introduction of artificial intelligence technology, realizes the real-time collection, intelligent analysis and precise control of key parameters in the oil extraction process, thereby improving the level of safe production, optimizing production efficiency, reducing operating costs and improving decision-making efficiency.

[0021] In one embodiment of the present invention, pressure data of a wellhead and a pipeline are collected in real time by a pressure sensor, and the pressure of the wellhead and the pipeline is adjusted according to the deviation between the pressure data of the wellhead and the pipeline and the production requirement index, including: S101, installing a first pressure sensor at each of multiple pressure monitoring positions at the wellhead; S102, installing a second pressure sensor at each of the multiple pressure detection node positions of the pipeline; S103, using the first pressure sensor to collect wellhead pressure data in real time, and regulating the wellhead pressure according to the deviation between the wellhead pressure data and the corresponding wellhead pressure production requirement index; S104: using the second pressure sensor to collect pipeline pressure data in real time, and regulating the pipeline pressure according to the deviation between the pipeline pressure data and the corresponding pipeline pressure production requirement index.

[0022] The working principle of the above technical solution is: a first pressure sensor is installed at each of the multiple key positions of the wellhead (such as the wellhead entrance, exit, key connection point, etc.) to collect the pressure data of the wellhead in real time. A second pressure sensor is installed at each of the multiple important nodes of the pipeline (such as the starting point, end point, branch point, turning point, etc. of the pipeline) to collect the pressure data of the pipeline in real time. These sensors are configured to continuously and stably transmit pressure data to the central control system or data processing unit. The first pressure sensor and the second pressure sensor respectively collect the pressure data of the wellhead and the pipeline in real time, and transmit these data to the central control system or data processing unit in the form of electrical signals or digital signals. The central control system or data processing unit receives and stores these pressure data for subsequent analysis and processing. The central control system or data processing unit analyzes the received pressure data in real time according to the preset wellhead and pipeline pressure production requirement indicators. By comparing the deviation between the actual pressure data and the production requirement indicators, the central control system or data processing unit can determine whether the pressure of the wellhead and the pipeline is within a safe and reasonable range. If the pressure data is found to be outside the preset range, the central control system or data processing unit will automatically trigger the control mechanism to adjust the operating status of valves, pumps and other equipment to control the pressure of the wellhead and pipeline in real time to keep the pressure within a safe range.

[0023] The effect of the above technical solution is: by real-time collection and analysis of wellhead and pipeline pressure data, the technical solution can timely detect and deal with potential pressure anomalies, thereby effectively preventing safety accidents caused by excessive or low pressure. By accurately regulating the pressure of the wellhead and pipeline, the technical solution can ensure the stability and continuity of the production process, thereby improving production efficiency. At the same time, reducing downtime or production reduction caused by pressure anomalies also helps to improve overall production efficiency. Through an intelligent pressure control mechanism, the technical solution can reduce equipment damage and maintenance costs caused by pressure anomalies. At the same time, by optimizing pressure control in the production process, energy consumption and operating costs can also be reduced. The technical solution realizes real-time collection, analysis and regulation of wellhead and pipeline pressures, and improves the level of automation of the production process. This helps to reduce the risk of manual intervention and misoperation, and improve the reliability and stability of the production process.

[0024] In summary, this technical solution realizes intelligent management and optimization of the production process by collecting real-time pressure data from wellheads and pipelines and accurately regulating the deviation between these data and production requirements. This not only improves production safety and production efficiency, but also reduces operating costs and improves automation.

[0025] In one embodiment of the present invention, the first pressure sensor is used to collect wellhead pressure data in real time, and the wellhead pressure is regulated according to the deviation between the wellhead pressure data and the corresponding wellhead pressure production requirement index, including: S1031, extracting the pressure data of the wellhead collected in real time by each of the first pressure sensors; S1032, comparing the deviation between the pressure data of each wellhead and its corresponding wellhead pressure production requirement index with a first pressure deviation threshold and a second pressure deviation threshold; S1033, when the deviation between the wellhead pressure data and the corresponding wellhead pressure production requirement index exceeds a preset first pressure deviation threshold, but does not exceed a second pressure deviation threshold, retrieve the historical pressure data collected by the first pressure sensor corresponding to the wellhead pressure data exceeding the preset first pressure deviation threshold; S1034, obtaining a pressure deviation evaluation coefficient using historical pressure data collected by a first pressure sensor corresponding to the wellhead pressure data exceeding a preset first pressure deviation threshold; S1035, comparing the pressure deviation evaluation coefficient with a preset pressure deviation evaluation threshold; S1036, when the pressure deviation evaluation coefficient exceeds a preset pressure deviation evaluation threshold, the pressure at the wellhead is regulated by increasing or reducing pressure according to the deviation between the pressure data at the wellhead exceeding the preset first pressure deviation threshold and the corresponding wellhead pressure production requirement index, so as to reduce the deviation between the pressure data at the wellhead and the corresponding wellhead pressure production requirement index; S1037. When the deviation between the wellhead pressure data and its corresponding wellhead pressure production requirement index exceeds a preset second pressure deviation threshold, the wellhead pressure is regulated by increasing or reducing the pressure according to the deviation between the wellhead pressure data exceeding the preset second pressure deviation threshold and its corresponding wellhead pressure production requirement index, so as to reduce the deviation between the wellhead pressure data and its corresponding wellhead pressure production requirement index.

[0026] The working principle of the above technical solution is: each first pressure sensor collects the pressure data of the wellhead where it is located in real time, and sends these data to the central control system or data processing unit. The central control system or data processing unit extracts the pressure data sent by each first pressure sensor for subsequent analysis and regulation. For the pressure data of each wellhead, the central control system or data processing unit calculates the deviation between it and the corresponding wellhead pressure production requirement index. The calculated deviation is compared with the preset first pressure deviation threshold and the second pressure deviation threshold to determine whether the deviation is within an acceptable range. When the deviation exceeds the first pressure deviation threshold but does not exceed the second pressure deviation threshold, the central control system or data processing unit will retrieve the historical pressure data collected by the first pressure sensor corresponding to the wellhead. Using these historical data, a pressure deviation evaluation coefficient is calculated to evaluate whether the current deviation is an abnormal or trend change. The calculated pressure deviation evaluation coefficient is compared with the preset pressure deviation evaluation threshold. If the evaluation coefficient exceeds the threshold, it means that the current deviation may be an abnormal or trend change that needs attention, and control measures need to be taken. According to the direction and size of the deviation, the pressure at the wellhead is regulated by increasing or reducing pressure to reduce the deviation so that it approaches or reaches the production requirement. When the deviation exceeds the second pressure deviation threshold, it means that the current pressure condition has seriously deviated from the production requirement and emergency control measures need to be taken immediately. According to the direction and size of the deviation, the pressure at the wellhead is also regulated by increasing or reducing pressure to quickly restore the pressure to a safe and reasonable range.

[0027] The effect of the above technical solution is: by real-time collection and analysis of wellhead pressure data, potential pressure anomalies can be discovered and handled in a timely manner, effectively preventing safety accidents caused by excessive or low pressure. Different control measures are taken according to different ranges of deviation, which not only ensures the timeliness of pressure control, but also avoids unnecessary energy consumption and equipment loss caused by excessive control. This technical solution realizes intelligent monitoring and control of wellhead pressure, reduces manual intervention, and improves the automation and intelligence level of the production process. By introducing historical data analysis and pressure deviation evaluation coefficients, a scientific basis is provided for control decisions, making control measures more accurate and effective. By accurately controlling the wellhead pressure, equipment damage and maintenance costs caused by pressure anomalies are reduced, while energy consumption is reduced, which helps to reduce overall operating costs.

[0028] In summary, this technical solution realizes intelligent management and optimization of the production process by real-time collection, analysis and regulation of wellhead pressure data, improves the level of safe production, optimizes pressure regulation, enhances the level of automation and intelligence, enhances the scientific nature of decision-making, and helps reduce operating costs.

[0029] In one embodiment of the present invention, the pressure deviation evaluation coefficient is obtained by using the historical pressure data collected by the first pressure sensor corresponding to the pressure data of the wellhead exceeding the preset first pressure deviation threshold, including: Step 1: when the number of first pressure sensors corresponding to the pressure data of the wellhead exceeding the preset first pressure deviation threshold is one, the first pressure sensor corresponding to the pressure data of the wellhead exceeding the preset first pressure deviation threshold is used as a target pressure sensor, and the historical pressure data collected by the target pressure sensor is retrieved; Step 2: Using the first evaluation coefficient model in combination with the historical pressure data collected by the target pressure sensor, obtain a pressure deviation evaluation coefficient; wherein the pressure deviation evaluation coefficient is obtained by the following formula: Among them, S 01 represents the pressure deviation evaluation coefficient obtained by the first evaluation coefficient model; a, b and c represent the preset first adjustment parameter, second adjustment parameter and third adjustment parameter respectively, and the value ranges of the first adjustment parameter, the second adjustment parameter and the third adjustment parameter are 0.58-1.13, 0.89-1.22 and 1.14-1.39; P b represents the pressure standard deviation corresponding to the historical pressure data collected by the target pressure sensor; n represents the number of pressure data of the historical pressure data; P i represents the pressure data value corresponding to the i-th historical pressure data; P i-1represents the pressure data value corresponding to the i-1th historical pressure data; P be Indicates the preset force standard deviation reference value; P fmaxi represents the maximum value of the pressure change amplitude between two adjacent pressure data collection moments corresponding to the i-th historical pressure data; P fmini Indicates the minimum value of the pressure change amplitude between two adjacent pressure data collection moments corresponding to the i-th historical pressure data; Step 3: When there are multiple first pressure sensors corresponding to the pressure data at the wellhead exceeding the preset first pressure deviation threshold, the first pressure sensor corresponding to the pressure data at the wellhead exceeding the preset first pressure deviation threshold is used as a target pressure sensor, and historical pressure data collected by the multiple target pressure sensors are retrieved; Step 4: Utilize the second evaluation coefficient model in combination with the historical pressure data collected by the target pressure sensors to obtain a pressure deviation evaluation coefficient; wherein the pressure deviation evaluation coefficient is obtained by the following formula: Among them, S 02 represents the pressure deviation evaluation coefficient obtained by the second evaluation coefficient model; m represents the number of target pressure sensors; P bi represents the standard deviation of the pressure data corresponding to the historical pressure data of the i-th target pressure sensor; G i represents the average value of the correlation coefficient between the i-th target pressure sensor and other target pressure sensors; w i represents the weight value corresponding to the i-th target pressure sensor; P fmax01i represents the maximum pressure change amplitude corresponding to the i-th target pressure sensor; P fmax02i The maximum value of the pressure variation amplitude of the target pressure sensor corresponding to the maximum value of the correlation coefficient of the i-th target pressure sensor.

[0030] The working principle of the above technical solution is: when the pressure data of only one first pressure sensor exceeds the preset first pressure deviation threshold, the sensor is determined as the target pressure sensor, and the historical pressure data collected by it is retrieved. When the pressure data of multiple first pressure sensors simultaneously exceed the preset first pressure deviation threshold, these sensors are all regarded as target pressure sensors, and the historical pressure data collected by them are retrieved respectively.

[0031] For a single target pressure sensor, the first evaluation coefficient model is used in combination with its historical pressure data to calculate the pressure deviation evaluation coefficient. This model takes into account factors such as the standard deviation of the historical pressure data, the number of pressure data, and the pressure change amplitude at the time of two adjacent pressure data collection, and performs weighted calculations through preset adjustment parameters. For multiple target pressure sensors, the second evaluation coefficient model is used to calculate the pressure deviation evaluation coefficient. This model not only takes into account the standard deviation of the historical pressure data of each target pressure sensor, but also takes into account the average value of the correlation coefficient between each sensor and the corresponding weight value, and also takes into account the maximum value of the pressure change amplitude of each sensor. These factors jointly determine the final pressure deviation evaluation coefficient.

[0032] The effect of the above technical solution is: by introducing historical pressure data and multiple evaluation factors (such as standard deviation, pressure change amplitude, correlation coefficient, etc.), the technical solution can more comprehensively evaluate the severity and potential risks of the current pressure deviation, thereby improving the accuracy of the evaluation. The pressure deviation evaluation coefficient, as an important basis for decision-making, can guide subsequent pressure control measures. By accurately calculating this coefficient, a more scientific control strategy can be formulated to avoid unnecessary energy consumption and equipment loss caused by excessive or insufficient control. The technical solution combines advanced mathematical models and algorithms to achieve intelligent monitoring and evaluation of wellhead pressure. This helps to improve the intelligence level of the entire production system, reduce manual intervention, and improve production efficiency and safety. By accurately evaluating the pressure deviation and taking corresponding control measures, equipment damage and maintenance costs caused by abnormal pressure can be effectively avoided. At the same time, the intelligent monitoring and evaluation system can also reduce energy consumption and operating costs and improve the economic benefits of the enterprise.

[0033] At the same time, by introducing the first evaluation coefficient model and the second evaluation coefficient model, combined with multiple statistical features of historical pressure data (such as pressure standard deviation, pressure change amplitude, etc.), the pressure deviation evaluation coefficient can be calculated more accurately, thereby more accurately reflecting the abnormal situation of wellhead pressure data. When multiple pressure sensors detect a pressure deviation exceeding the preset threshold, the scheme can comprehensively consider the data of these sensors, and improve the accuracy and comprehensiveness of the evaluation coefficient by calculating the average value and weight value of the correlation coefficient. The scheme can handle the situation where a single or multiple pressure sensors detect a pressure deviation, and flexibly respond to different monitoring scenarios through different evaluation coefficient models. The first adjustment parameter, the second adjustment parameter, and the third adjustment parameter in the formula have a clear value range, which can be adjusted according to actual conditions to adapt to different monitoring needs and pressure data characteristics. Using historical pressure data for evaluation can eliminate the influence of accidental factors on the data and improve the reliability and stability of the evaluation results. By comprehensively considering multiple statistical features such as pressure standard deviation and pressure change amplitude, the abnormal situation of pressure data can be more comprehensively evaluated, reducing the possibility of false alarms and missed reports. At the same time, the scheme realizes the automatic processing of the pressure deviation evaluation coefficient through model calculation and formula derivation, reducing manual intervention and calculation workload. The design of the formulas and models is relatively simple and clear, easy to understand and implement, and convenient for promotion and use in practical applications.

[0034] In summary, the technical solution has shown significant technical effects in terms of accuracy, flexibility, reliability and ease of operation. These effects have jointly improved the accuracy and efficiency of the abnormal evaluation of wellhead pressure data, and provided strong technical support for safety monitoring in the process of oil extraction and production. At the same time, the technical solution calculates the pressure deviation evaluation coefficient by introducing historical pressure data and multiple evaluation factors, thus realizing accurate evaluation and intelligent monitoring of wellhead pressure. This not only improves the accuracy of evaluation and the scientific nature of decision-making, but also improves the intelligence level of the system and reduces operating costs.

[0035] In one embodiment of the present invention, the second pressure sensor is used to collect pipeline pressure data in real time, and the pipeline pressure is regulated according to the deviation between the pipeline pressure data and the corresponding pipeline pressure production requirement index, including: S1041, retrieve the pipeline pressure data collected by the second pressure sensor in real time; S1042, comparing the pressure data of each pipeline with its corresponding pressure risk threshold and pressure warning threshold; S1043, when the pressure data of the pipeline exceeds the corresponding pressure warning threshold, directly adjusting the pipeline valve corresponding to the pressure detection node position of the pipeline where the pressure data exceeds the corresponding pressure warning threshold, so as to reduce the pressure value corresponding to the pressure detection node position of the pipeline; S1044. When the pressure data of the pipeline exceeds its corresponding pressure risk threshold, the target pressure detection node position is screened out from the pressure detection node positions of all pipelines, and the target pressure data corresponding to the target pressure detection node position is used to obtain the pressure risk assessment coefficient, and the pressure control judgment of the pressure detection node position is performed using the pressure risk assessment coefficient.

[0036] The working principle of the above technical solution is: the pressure data of the pipeline is collected in real time by installing a second pressure sensor at the key node of the pipeline. The collected pressure data is compared with the corresponding pressure risk threshold and pressure warning threshold. These two thresholds are set according to factors such as the production requirements, safety standards and historical data of the pipeline. When the pressure data of the pipeline exceeds the pressure warning threshold, the system will automatically trigger the warning mechanism and directly adjust the pipeline valve corresponding to the pressure detection node position of the pipeline where the pressure data exceeds the warning threshold to reduce the pressure value at this position to prevent the pressure from continuing to rise. When the pressure data of the pipeline exceeds the pressure risk threshold, it means that the pipeline may face serious pressure risks. At this time, the system will screen out the target pressure detection node position from the pressure detection node positions of all pipelines, and use the pressure data corresponding to these positions to calculate the pressure risk evaluation coefficient. The pressure control judgment of the pressure detection node position is carried out by this coefficient to determine whether further control measures are needed.

[0037] The effect of the above technical solution is: by real-time monitoring and regulating the pressure of the pipeline, it can effectively avoid water supply interruption, water quality problems, pipe burst and other safety hazards caused by excessive or low pressure, and improve the operation safety of the pipeline. The technical solution can automatically adjust the valve opening according to the actual pressure of the pipeline to achieve optimal pressure control of the pipeline. This can not only reduce energy consumption and operating costs, but also improve the stability and reliability of water supply. The technical solution combines sensor technology, data processing technology and automatic control technology to realize intelligent management of pipelines. Through the visual monitoring interface and data analysis tools, managers can understand the pressure status of the pipeline in real time and perform remote regulation, which improves management efficiency and response speed. By setting the pressure warning threshold and pressure risk threshold, the technical solution can issue a warning in time and take regulatory measures when the pipeline pressure is abnormal, effectively preventing the occurrence of pressure problems. At the same time, when pressure problems occur, they can also respond quickly to reduce losses and impacts.

[0038] In summary, this technical solution realizes intelligent management and optimized operation of pipelines by real-time monitoring and regulation of pipeline pressure data, thereby improving the safety and stability of water supply.

[0039] In one embodiment of the present invention, when the pressure data of the pipeline exceeds the corresponding pressure risk threshold, a target pressure detection node position is screened out from the pressure detection node positions of all pipelines, and a pressure risk evaluation coefficient is obtained using the target pressure data corresponding to the target pressure detection node position, and a pressure control determination of the pressure detection node position is performed using the pressure risk evaluation coefficient, including: Step 1: When the pressure data of the pipeline exceeds the corresponding pressure risk threshold, the correlation coefficient between the pressure detection node position of the pipeline whose pressure data exceeds the corresponding pressure risk threshold and the pressure detection node positions of other pipelines is retrieved; Step 2: Retrieve the pressure detection node positions of the pipelines whose pressure data exceeds the corresponding pressure risk threshold and the pressure detection node positions of other pipelines whose correlation coefficients exceed the preset correlation coefficient threshold as the target pressure detection node positions, and use the pressure data corresponding to the target pressure detection node positions as the target pressure data; Step 3: Obtain a pressure risk assessment coefficient using the pressure data of the pipeline corresponding to the pressure detection node position of the pipeline where the pressure data of the pipeline exceeds the corresponding pressure risk threshold and its corresponding target pressure data; The pressure risk assessment coefficient is obtained by the following formula: Where K represents the pressure risk assessment coefficient; k represents the number of target pressure detection node locations; P g The pressure data of the pipeline corresponding to the pressure detection node position of the pipeline where the pressure data of the pipeline exceeds the corresponding pressure risk threshold; P gi represents the target pressure data corresponding to the position of the i-th target pressure detection node; F i represents the correlation coefficient between the pressure detection node position of the pipeline whose pressure data exceeds its corresponding pressure risk threshold and the i-th target pressure detection node position; δ represents the preset time attenuation coefficient; t i represents the total pressure data collection time corresponding to the i-th target pressure detection node position; λ 01 and λ 02 represent the first risk factor and the second risk factor respectively, and the first risk factor is obtained by the following formula: Among them, λ 01represents the first risk factor; F i The correlation coefficient between the pressure detection node position of the pipeline whose pressure data exceeds its corresponding pressure risk threshold and the i-th target pressure detection node position; F y Indicates the preset correlation coefficient threshold; F max Indicates the maximum value of the correlation coefficient between the pressure detection node positions of the pipeline corresponding to the n target pressure detection node positions and the pressure data of the pipeline exceeding the corresponding pressure risk threshold; Furthermore, the second risk factor is obtained by the following formula: Among them, λ 02 represents the second risk factor; P gb The standard deviation of the pressure data corresponding to the pressure detection node position of the pipeline where the pressure data of the pipeline exceeds the corresponding pressure risk threshold; P gbi represents the standard deviation of the pressure data corresponding to the position of the i-th target pressure detection node; F i The correlation coefficient between the pressure detection node position of the pipeline indicating that the pressure data of the pipeline exceeds the corresponding pressure risk threshold and the i-th target pressure detection node position; Step 4: Compare the stress risk assessment coefficient with a preset stress risk assessment threshold; Step 5. When the pressure risk assessment coefficient exceeds the preset pressure risk assessment threshold, the pipeline valve corresponding to the pressure detection node position of the pipeline whose pressure data exceeds its corresponding pressure warning threshold is adjusted to reduce the pressure value corresponding to the pressure detection node position of the pipeline.

[0040] The working principle of the above technical solution is: when the pressure data of a pipeline exceeds its corresponding pressure risk threshold, the correlation coefficient between the pipeline pressure detection node position and other pipeline pressure detection node positions is first retrieved. Then, other pipeline pressure detection node positions that exceed the preset correlation coefficient threshold are selected from these correlation coefficients as target pressure detection node positions. The pressure data corresponding to these target pressure detection node positions are used as target pressure data.

[0041] The pressure risk assessment coefficient is calculated by using the pipeline pressure data exceeding the pressure risk threshold and its corresponding target pressure data, combined with the correlation coefficient, time decay coefficient, total pressure data collection time, and the first risk factor and the second risk factor. The first risk factor takes into account the relationship between the correlation coefficient and the preset threshold and the maximum correlation coefficient, reflecting the strength of the correlation between the target pressure detection node position and the pipeline pressure detection node position exceeding the risk threshold. The second risk factor takes into account the relationship between the standard deviation of the pipeline pressure data exceeding the risk threshold and the standard deviation of the target pressure data, as well as the correlation coefficient between them, reflecting the volatility and correlation of the pressure data.

[0042] The calculated pressure risk assessment coefficient is compared with the preset pressure risk assessment threshold. If the pressure risk assessment coefficient exceeds the preset threshold, it is determined that pressure control measures need to be taken. The specific control measures are to adjust the pipeline valve corresponding to the pipeline pressure detection node position where the pressure data exceeds its corresponding pressure warning threshold to reduce the pipeline pressure.

[0043] The effect of the above technical solution is: by comprehensively considering multiple factors (such as correlation coefficient, time decay coefficient, standard deviation of pressure data, etc.), the calculated pressure risk evaluation coefficient can more accurately reflect the pressure risk status of the pipeline. According to the coefficient, the pressure control judgment can more accurately determine the pipelines and their locations where control measures need to be taken, and avoid excessive or insufficient control. Timely discovery and treatment of pipelines that exceed the pressure risk threshold can effectively prevent safety accidents such as pipeline rupture and leakage caused by excessive pressure. By adjusting the pipeline valve to reduce the pressure, it can ensure that the pipeline operates within a safe range and ensure the smooth progress of production activities such as water supply. Reasonable pressure control can reduce energy consumption and pipeline wear and extend the service life of the pipeline. At the same time, by optimizing the pressure distribution, the efficiency and quality of production activities such as water supply can be improved. This technical solution combines sensor technology, data processing technology and automatic control technology to realize intelligent monitoring and management of pipelines. Through the visual monitoring interface and data analysis tools, managers can understand the pressure status of the pipeline in real time and perform remote control, which improves management efficiency and response speed.

[0044] At the same time, by retrieving the data of other pipeline pressure detection nodes related to abnormal pressure data and calculating the correlation coefficient between them, the pressure abnormality can be evaluated more comprehensively and the accuracy of risk assessment can be improved. The introduction of the pressure risk evaluation coefficient K comprehensively considers multiple factors such as target pressure data, correlation coefficient, time decay coefficient and risk factor, making the risk assessment more comprehensive and accurate. The calculation of the first risk factor λ01 and the second risk factor λ02 takes into account the correlation coefficient and its maximum value, the standard deviation of the pressure data, etc., and can be dynamically adjusted according to the actual situation to improve the flexibility and accuracy of risk assessment.

[0045] When the pipeline pressure data exceeds the risk threshold, the target pressure detection node position can be quickly screened out, and the pressure risk assessment coefficient can be calculated to achieve real-time response and rapid regulation. According to the comparison result of the pressure risk assessment coefficient and the preset threshold, the valve of the corresponding pipeline is intelligently adjusted to reduce the pressure value and realize intelligent pressure regulation. By comprehensively considering multiple factors, the accuracy of risk assessment is improved, and improper pressure regulation caused by false alarms or omissions is reduced. The solution can handle different pipelines, different pressure detection node positions and different pressure data characteristics, and has strong adaptability and versatility. By introducing the time decay coefficient δ, the influence of time factors on pressure data is considered, making risk assessment more stable and reliable. The solution has a clear structure, is easy to maintain and expand, and can be upgraded and optimized according to actual needs. Through intelligent pressure regulation, equipment damage and safety accidents caused by abnormal pressure are reduced, and maintenance costs are reduced. Timely pressure regulation can ensure the normal operation of the pipeline, improve production efficiency, and provide strong support for the sustainable development of the enterprise.

[0046] In summary, the technical solution has shown significant technical effects in terms of accurate risk assessment, efficient pressure control, enhanced system robustness, economy and practicality. These effects have jointly improved the intelligent level of pipeline pressure monitoring and control, and provided strong guarantees for the safe production and efficient operation of enterprises. At the same time, the technical solution achieves accurate control and intelligent management of pipeline pressure by screening the target pressure detection node location, calculating the pressure risk evaluation coefficient and making pressure control judgments, thereby improving the safety and operation efficiency of the pipeline.

[0047] In one embodiment of the present invention, the vibration operation parameters of each production equipment are collected in real time by a sensor group, and the operation of the equipment is safely regulated according to the vibration operation parameters of each production equipment, including: S301, collecting vibration operation parameters of each production equipment in real time through a sensor group, wherein the sensor group includes an acceleration sensor, a velocity sensor and a displacement sensor, and the vibration operation parameters include vibration acceleration, vibration velocity and vibration displacement generated by vibration; S302, comparing the vibration acceleration, vibration velocity and vibration displacement generated by the vibration of each production equipment with the corresponding acceleration threshold, velocity threshold and vibration displacement threshold respectively; S303, when any one of the vibration acceleration, vibration velocity and vibration displacement generated by the vibration exceeds its corresponding threshold value, it is determined whether it is necessary to perform safety regulation on the production equipment; S304: When it is determined that the production equipment needs to be safely regulated, the production equipment is decelerated.

[0048] The working principle of the above technical solution is: the vibration operating parameters of each production equipment are collected in real time through a sensor group (including an acceleration sensor, a velocity sensor and a displacement sensor), and these parameters specifically include vibration acceleration, vibration velocity and vibration displacement generated by vibration. The collected vibration acceleration, vibration velocity and vibration displacement are compared with their corresponding acceleration threshold, velocity threshold and vibration displacement threshold. These thresholds are set based on factors such as the performance, safety standards and historical data of the production equipment, and are used to determine whether the production equipment is in normal operation. When any parameter of vibration acceleration, vibration velocity and vibration displacement exceeds its corresponding threshold, the system will automatically trigger the safety control judgment mechanism. The system will decide whether it is necessary to perform safety control on the production equipment according to the preset judgment logic (such as the duration of the parameter exceeding the threshold, the degree of exceeding the threshold, etc.). If it is determined that the production equipment needs to be safely regulated, the system will execute deceleration control measures. Deceleration control can be achieved by adjusting the operating speed or power of the production equipment to reduce the vibration level of the production equipment and ensure its safe operation.

[0049] The effect of the above technical solution is: by real-time monitoring of the vibration operating parameters of the production equipment and taking deceleration control measures in time when the parameters exceed the threshold, equipment damage, production interruption and even safety accidents caused by excessive equipment vibration can be effectively avoided. Reasonable deceleration control can ensure that the production equipment operates at a safe vibration level while avoiding unnecessary downtime and maintenance costs. This helps to maintain the continuity and stability of the production line and improve production efficiency. Vibration acceleration, vibration velocity and vibration displacement are important indicators reflecting the operating status of production equipment. By real-time monitoring of these parameters, potential signs of equipment failure can be discovered in time, and measures can be taken for prevention and maintenance, thereby extending the service life of the equipment. This technical solution combines sensor technology, data processing technology and automatic control technology to realize intelligent monitoring and management of production equipment. Through the visual monitoring interface and data analysis tools, managers can understand the vibration status of production equipment in real time and perform remote control, improving management efficiency and response speed.

[0050] In summary, this technical solution realizes accurate monitoring and management of the equipment's operating status by real-time monitoring of the vibration operating parameters of production equipment and performing safety regulation, thereby improving the equipment's safety, production efficiency, and intelligent management level.

[0051] In one embodiment of the present invention, when any one of the vibration acceleration, vibration velocity and vibration displacement generated by the vibration exceeds its corresponding threshold value, it is determined whether the production equipment needs to be safely regulated, including: S3031. When any one of the vibration acceleration, vibration velocity, and vibration displacement generated by vibration exceeds its corresponding threshold, the corresponding time when any one of the vibration acceleration, vibration velocity, and vibration displacement generated by vibration exceeds its corresponding threshold is used as the data retrieval time; S3032, from the moment of data retrieval, retrieve the vibration operation parameters of the production equipment in real time; wherein the vibration operation parameters include vibration acceleration, vibration velocity and vibration displacement generated by vibration; S3033, obtaining a vibration operation evaluation coefficient using the vibration operation parameters of the production equipment; The vibration operation evaluation coefficient is obtained by the following formula: Among them, U represents the vibration operation evaluation coefficient; A, V and D represent vibration acceleration, vibration velocity and vibration displacement caused by vibration respectively; RMS (A, V, D) represents the sum of the square root values ​​of vibration acceleration, vibration velocity and vibration displacement caused by vibration; MAD (A, V, D) represents the sum of the mean absolute deviation values ​​of vibration acceleration, vibration velocity and vibration displacement caused by vibration; STD (A, V, D) represents the sum of the standard deviations of vibration acceleration, vibration velocity and vibration displacement caused by vibration; Var (A, V, D) represents the sum of the variances of vibration acceleration, vibration velocity and vibration displacement caused by vibration; K b represents a preset basic adjustment coefficient, and the value range of the basic adjustment coefficient is 1.32-1.47; σ represents a preset scaling factor, and the value range of the scaling factor is 0.18-0.53; ε represents a preset minimum constant, which is used to prevent the denominator from being zero; S3034, comparing the vibration operation evaluation coefficient with a preset vibration operation evaluation coefficient threshold; S3035. When the vibration operation evaluation coefficient exceeds the preset vibration operation evaluation coefficient, it is determined that safety regulation of the production equipment is required.

[0052] The working principle of the above technical solution is: when any parameter of vibration acceleration, vibration velocity and vibration displacement generated by vibration exceeds its corresponding threshold, the moment is used as the data retrieval moment. This means that the system has detected a possible abnormal vibration situation. From the moment of data retrieval, the system starts to retrieve the vibration operation parameters of the production equipment in real time, including vibration acceleration, vibration velocity and vibration displacement generated by vibration. The real-time nature of these data is crucial for subsequent analysis and judgment. Using the vibration operation parameters retrieved in real time, the system calculates the vibration operation evaluation coefficient. This coefficient is a comprehensive indicator used to evaluate the vibration operation status of the production equipment. During the calculation process, the system considers the square root value (RMS) and mean absolute deviation value (MAD) of vibration acceleration, vibration velocity and vibration displacement, and weights and scales them by the preset basic adjustment coefficient (Kb), scaling coefficient (σ) and minimum constant (ε). The system compares the calculated vibration operation evaluation coefficient with the preset vibration operation evaluation coefficient threshold. This threshold is set based on factors such as the performance, safety standards and historical data of the production equipment, and is used to determine whether the production equipment is in a state that requires safe regulation. If the vibration operation evaluation coefficient exceeds the preset vibration operation evaluation coefficient threshold, the system determines that the production equipment needs to be safely regulated. This may include deceleration, shutdown, alarm or other safety measures to ensure the safe operation of the production equipment.

[0053] The effect of the above technical solution is: by real-time monitoring of the vibration operating parameters of production equipment and calculating the vibration operation evaluation coefficient, the system can promptly detect potential vibration anomalies, thereby taking necessary safety measures to avoid equipment damage, production interruptions and even safety accidents. The vibration operation evaluation coefficient provides a quantitative indicator for evaluating the vibration operation status of production equipment. This helps managers develop more reasonable maintenance plans and reduce unnecessary downtime and maintenance costs.

[0054] This technical solution combines sensor technology, data processing technology and automatic control technology to realize intelligent monitoring and management of production equipment. Through the visual monitoring interface and data analysis tools, managers can understand the vibration status of production equipment in real time and conduct remote control. Timely vibration anomaly detection and control help maintain the continuity and stability of the production line, thereby improving production efficiency. In addition, by optimizing maintenance strategies, production interruption time caused by equipment failure can also be reduced. Vibration acceleration, vibration velocity and vibration displacement are important indicators that reflect the operating status of production equipment. By monitoring these parameters in real time and calculating the vibration operation evaluation coefficient, potential signs of equipment failure can be discovered in time, and measures can be taken for prevention and maintenance, thereby extending the service life of the equipment.

[0055] The scheme can immediately use the data retrieval moment as the time when any parameter of vibration acceleration, vibration velocity or vibration displacement exceeds the threshold, and retrieve the vibration operation parameters of the production equipment in real time. This real-time monitoring method can quickly capture the abnormal state of the production equipment, making it possible to take timely control measures. By calculating the vibration operation evaluation coefficient and comparing it with the preset threshold, once the threshold is exceeded, it is determined that the production equipment needs to be safely regulated. This rapid response mechanism can effectively reduce the occurrence of equipment failures and ensure production safety. The vibration operation evaluation coefficient comprehensively considers the three parameters of vibration acceleration, vibration velocity and vibration displacement. Through the calculation of the square root value and the mean absolute deviation value, it can more comprehensively reflect the vibration state of the production equipment. This comprehensive evaluation method improves the accuracy and reliability of the evaluation. According to the calculation results of the vibration operation evaluation coefficient, it can be flexibly determined whether the production equipment needs to be safely regulated. This data-driven control method is more scientific and reasonable, and can avoid unnecessary downtime and maintenance costs. Parameters such as the basic adjustment coefficient, scaling coefficient and minimum constant in the formula can be adjusted and optimized according to actual conditions to meet the needs of different production equipment and different working environments. This parameter optimization method improves the flexibility and applicability of the scheme. By introducing the minimum constant ε, the denominator is prevented from being zero, ensuring the stability and reliability of the formula. At the same time, the calculation of the square root value and the mean absolute deviation value also has a certain anti-interference ability, which can reduce the impact of noise and outliers on the evaluation results. This solution does not require large-scale transformation or upgrading of production equipment. It only needs to add vibration sensors and data acquisition modules to the existing equipment to achieve real-time monitoring and evaluation. This implementation method is simple and convenient, easy to promote and apply. Since the solution mainly relies on data acquisition and calculation, the maintenance cost is relatively low. At the same time, the accuracy and stability of the solution can be maintained by regularly calibrating sensors and updating algorithms.

[0056] In summary, the technical solution has shown significant technical effects in real-time monitoring and response, precise evaluation and regulation, parameter optimization and stability, and easy implementation and maintenance. These effects have jointly improved the operational safety and reliability of production equipment, providing a strong guarantee for the production safety and efficient operation of enterprises. At the same time, the technical solution realizes precise monitoring and management of the equipment operation status by real-time monitoring of the vibration operation parameters of production equipment and calculating the vibration operation evaluation coefficient, thereby improving the safety, production efficiency and intelligent management level of the equipment.

[0057] In one embodiment of the present invention, when it is determined that safety regulation of production equipment is required, deceleration regulation of the production equipment is performed, including: S3041. When it is determined that safety regulation of production equipment is required, the vibration operation evaluation coefficient is retrieved; S3042, using the vibration operation evaluation coefficient to obtain a deceleration control ratio of the production equipment, and performing deceleration control on the production equipment according to the deceleration control ratio of the production equipment; The deceleration control ratio of the production equipment is obtained by the following formula: Among them, B represents the deceleration control ratio of the production equipment; r represents the preset proportional adjustment coefficient, and the value range of the proportional adjustment coefficient is 0.27-0.34; U represents the vibration operation evaluation coefficient.

[0058] The working principle of the above technical solution is: when the system determines that the production equipment needs to be safely regulated, it will first retrieve the previously calculated vibration operation evaluation coefficient U. This coefficient reflects the current vibration operation status of the production equipment and is an important basis for determining the deceleration regulation ratio. Using the vibration operation evaluation coefficient U and the preset proportional adjustment coefficient r, the deceleration regulation ratio B of the production equipment is calculated by the formula. The proportional adjustment coefficient r is a value set based on experience or experimental data, which is used to adjust the sensitivity of the deceleration regulation ratio. According to the calculated deceleration regulation ratio B, the system will decelerate the production equipment. This is usually achieved by adjusting the operating speed or power of the production equipment to reduce its vibration level and ensure safe operation.

[0059] The effect of the above technical solution is: through the deceleration control based on the vibration operation evaluation coefficient, the technical solution can more accurately determine whether the production equipment needs to be decelerated, thereby avoiding damage to the equipment, production interruption or safety accidents caused by excessive vibration. The deceleration control is carried out under the premise of ensuring safety, so it will not excessively affect the production efficiency. At the same time, by timely deceleration, long-term downtime caused by equipment failure can be avoided, thereby maintaining the continuity and stability of the production line. The technical solution combines sensor technology, data processing technology and automatic control technology to realize intelligent monitoring and management of production equipment. Through automatic calculation and control, manual intervention is reduced, and management efficiency and response speed are improved. By real-time monitoring of vibration operation parameters and calculating vibration operation evaluation coefficients, the system can timely detect potential vibration anomalies of the equipment and take measures for prevention and maintenance. Deceleration control is one of the preventive measures that helps to extend the service life of the equipment. Long-term vibration anomalies may lead to reduced equipment performance and reliability. Through timely deceleration control, the wear and fatigue of the equipment caused by vibration can be reduced, thereby improving its overall reliability and stability.

[0060] In summary, this technical solution achieves accurate monitoring and management of the vibration state of production equipment through deceleration control based on the vibration operation evaluation coefficient, improves the safety, production efficiency and intelligent management level of the equipment, and also helps prevent failures and improve equipment reliability.

[0061] An AI-based production safety control system is proposed in an embodiment of the present invention. Figure 2 As shown, the AI-based safe production control system includes: The AI-based safe production control system includes: The first adjustment module is used to collect the pressure data of the wellhead and the pipeline in real time through the pressure sensor, and adjust the pressure of the wellhead and the pipeline according to the deviation between the pressure data of the wellhead and the pipeline and the production requirement index; The first safety warning module is used to issue a safety warning when the deviation between the pressure data of the wellhead and the pipeline and the production requirement index still cannot meet the preset deviation requirement after the pressure of the wellhead and the pipeline is regulated; A second adjustment module is used to collect the vibration operation parameters of each production equipment in real time through a sensor group, and to safely regulate the operation of the equipment according to the vibration operation parameters of each production equipment; The second safety warning module is used to issue a safety warning to the production equipment whose vibration operation still cannot meet its corresponding vibration operation standard after each production equipment completes safety regulation.

[0062] The working principle of the above technical solution is as follows: pressure sensors are deployed at the wellhead and pipeline to collect pressure data at these key locations in real time. The collected pressure data is input into the AI ​​system, and the system calculates the deviation between the pressure data and the production requirements according to the preset production requirements. According to the deviation, the AI ​​system adjusts the pressure of the wellhead and pipeline in real time by controlling valves, pumps and other regulating equipment to keep the pressure within a safe range. After completing the pressure regulation, the AI ​​system will check the deviation between the pressure data of the wellhead and pipeline and the production requirements again. If the deviation still cannot meet the preset deviation requirements (that is, it exceeds the safety range), the AI ​​system will trigger the safety warning mechanism, issue an alarm to the operator, and may automatically take further emergency measures. The sensor group is deployed on each production equipment to collect the vibration operating parameters of the equipment (such as amplitude, frequency, etc.) in real time. According to the preset vibration operating standards, the AI ​​system analyzes the vibration operating parameters of each equipment and determines whether the equipment is in normal operation. If it is found that the vibration operating parameters of the equipment exceed the standard range, the AI ​​system will control the equipment in real time by controlling the operating parameters of the equipment (such as speed, load, etc.) to keep the equipment in a safe operating state. After completing the equipment operation control, the AI ​​system will check again whether the vibration operation parameters of each device meet the corresponding vibration operation standards. If there are still devices whose vibration operation parameters cannot meet the standards (that is, the equipment is still in an abnormal state), the AI ​​system will trigger the safety warning mechanism, send an alarm to the operator, and may recommend shutdown for maintenance or take other necessary measures.

[0063] The effect of the above technical solution is: by real-time collection and analysis of the operating data of the wellhead, pipeline and production equipment, the AI ​​system can promptly discover and deal with potential safety hazards, thereby greatly reducing the probability of safety accidents. The AI ​​system can accurately control the pressure of the wellhead and pipeline according to the production requirements to ensure the stability and continuity of the production process. At the same time, by real-time control of the vibration operating parameters of the production equipment, the equipment can be prevented from being shut down or damaged due to abnormal vibration, thereby improving the utilization rate and production efficiency of the equipment. Through intelligent production safety control methods, enterprises can reduce losses and downtime caused by safety accidents and equipment failures. At the same time, the application of AI systems can also help enterprises optimize resource allocation and reduce maintenance costs. The AI ​​system can provide key production data and analysis results in real time, providing a scientific basis for the company's decision-making. This helps companies quickly respond to market changes and changes in production demand, thereby formulating more reasonable production plans and strategies.

[0064] In summary, this technical solution, through the introduction of artificial intelligence technology, realizes the real-time collection, intelligent analysis and precise control of key parameters in the oil extraction process, thereby improving the level of safe production, optimizing production efficiency, reducing operating costs and improving decision-making efficiency.

[0065] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A safety production control method based on AI, characterized in that: The AI-based safe production control method includes: The pressure sensor collects the pressure data of the wellhead and pipeline in real time, and adjusts the pressure of the wellhead and pipeline according to the deviation between the pressure data of the wellhead and pipeline and the production requirement index; After the pressure of the wellhead and pipeline is regulated, if the deviation between the pressure data of the wellhead and pipeline and the production requirement index still cannot meet the preset deviation requirement, a safety warning will be issued; The vibration operating parameters of each production equipment are collected in real time through the sensor group, and the operation of the equipment is safely regulated according to the vibration operating parameters of each production equipment; When each production equipment completes safety regulation, if the vibration operation of each production equipment still cannot meet its corresponding vibration operation standard, a safety warning is issued for the production equipment whose vibration operation still cannot meet its corresponding vibration operation standard.

2. The AI-based production safety control method according to claim 1 is characterized in that: The pressure sensor collects the pressure data of the wellhead and pipeline in real time, and adjusts the pressure of the wellhead and pipeline according to the deviation between the pressure data of the wellhead and pipeline and the production requirement index, including: A first pressure sensor is installed at each of the multiple pressure monitoring positions at the wellhead; A second pressure sensor is installed at each of the multiple pressure detection node positions of the pipeline; Using the first pressure sensor to collect wellhead pressure data in real time, and regulating the wellhead pressure according to the deviation between the wellhead pressure data and the corresponding wellhead pressure production requirement index; The second pressure sensor is used to collect pipeline pressure data in real time, and the pipeline pressure is regulated according to the deviation between the pipeline pressure data and the corresponding pipeline pressure production requirement index.

3. The AI-based production safety control method according to claim 2 is characterized in that: The first pressure sensor is used to collect the pressure data of the wellhead in real time, and the pressure of the wellhead is regulated according to the deviation between the pressure data of the wellhead and the corresponding wellhead pressure production requirement index, including: Extracting the wellhead pressure data collected in real time by each of the first pressure sensors; Compare the deviation between the pressure data of each wellhead and its corresponding wellhead pressure production requirement index with a first pressure deviation threshold and a second pressure deviation threshold; When the deviation between the wellhead pressure data and the corresponding wellhead pressure production requirement index exceeds a preset first pressure deviation threshold, but does not exceed a second pressure deviation threshold, the historical pressure data collected by the first pressure sensor corresponding to the wellhead pressure data exceeding the preset first pressure deviation threshold is retrieved; Obtaining a pressure deviation evaluation coefficient using historical pressure data collected by a first pressure sensor corresponding to the wellhead pressure data exceeding a preset first pressure deviation threshold; comparing the pressure deviation evaluation coefficient with a preset pressure deviation evaluation threshold; When the pressure deviation evaluation coefficient exceeds the preset pressure deviation evaluation threshold, the pressure at the wellhead is regulated by increasing or reducing pressure according to the deviation between the pressure data at the wellhead exceeding the preset first pressure deviation threshold and the corresponding wellhead pressure production requirement index, so as to reduce the deviation between the pressure data at the wellhead and the corresponding wellhead pressure production requirement index; When the deviation between the wellhead pressure data and its corresponding wellhead pressure production requirement index exceeds a preset second pressure deviation threshold, the wellhead pressure is regulated by increasing or reducing the pressure according to the deviation between the wellhead pressure data exceeding the preset second pressure deviation threshold and its corresponding wellhead pressure production requirement index, so as to reduce the deviation between the wellhead pressure data and its corresponding wellhead pressure production requirement index.

4. The AI-based production safety control method according to claim 3 is characterized in that: Obtaining a pressure deviation evaluation coefficient using historical pressure data collected by a first pressure sensor corresponding to the wellhead pressure data exceeding a preset first pressure deviation threshold value comprises: When the number of first pressure sensors corresponding to the pressure data of the wellhead exceeding the preset first pressure deviation threshold is one, the first pressure sensor corresponding to the pressure data of the wellhead exceeding the preset first pressure deviation threshold is used as a target pressure sensor, and the historical pressure data collected by the target pressure sensor is retrieved; The pressure deviation evaluation coefficient is obtained by using the first evaluation coefficient model in combination with the historical pressure data collected by the target pressure sensor; wherein the pressure deviation evaluation coefficient is obtained by the following formula: Among them, S 01 represents the pressure deviation evaluation coefficient obtained by the first evaluation coefficient model; a, b and c represent the preset first adjustment parameter, second adjustment parameter and third adjustment parameter respectively, and the value ranges of the first adjustment parameter, the second adjustment parameter and the third adjustment parameter are 0.58-1.13, 0.89-1.22 and 1.14-1.39; P b represents the pressure standard deviation corresponding to the historical pressure data collected by the target pressure sensor; n represents the number of pressure data of the historical pressure data; P i represents the pressure data value corresponding to the i-th historical pressure data; P i-1 represents the pressure data value corresponding to the i-1th historical pressure data; P be Indicates the preset force standard deviation reference value; P fmaxi represents the maximum value of the pressure change amplitude between two adjacent pressure data collection moments corresponding to the i-th historical pressure data; P fmini Indicates the minimum value of the pressure change amplitude between two adjacent pressure data collection moments corresponding to the i-th historical pressure data; When there are multiple first pressure sensors corresponding to the pressure data at the wellhead exceeding the preset first pressure deviation threshold, the first pressure sensor corresponding to the pressure data at the wellhead exceeding the preset first pressure deviation threshold is used as a target pressure sensor, and historical pressure data collected by the multiple target pressure sensors are retrieved; The pressure deviation evaluation coefficient is obtained by using the second evaluation coefficient model in combination with the historical pressure data collected by the plurality of target pressure sensors; wherein the pressure deviation evaluation coefficient is obtained by the following formula: Among them, S 02 represents the pressure deviation evaluation coefficient obtained by the second evaluation coefficient model; m represents the number of target pressure sensors; P bi represents the standard deviation of the pressure data corresponding to the historical pressure data of the i-th target pressure sensor; G i represents the average value of the correlation coefficient between the i-th target pressure sensor and other target pressure sensors; w i represents the weight value corresponding to the i-th target pressure sensor; P fmax01i represents the maximum pressure change amplitude corresponding to the i-th target pressure sensor; P fmax02i The maximum value of the pressure variation amplitude of the target pressure sensor corresponding to the maximum value of the correlation coefficient of the i-th target pressure sensor.

5. The AI-based production safety control method according to claim 2 is characterized in that: The second pressure sensor is used to collect the pressure data of the pipeline in real time, and the pressure of the pipeline is regulated according to the deviation between the pressure data of the pipeline and the corresponding pipeline pressure production requirement index, including: Retrieving pipeline pressure data collected by the second pressure sensor in real time; Compare the pressure data of each pipeline with its corresponding pressure risk threshold and pressure warning threshold; When the pressure data of the pipeline exceeds the corresponding pressure warning threshold, the pipeline valve corresponding to the pressure detection node position of the pipeline where the pressure data exceeds the corresponding pressure warning threshold is directly adjusted to reduce the pressure value corresponding to the pressure detection node position of the pipeline; When the pressure data of the pipeline exceeds its corresponding pressure risk threshold, the target pressure detection node position is screened out from the pressure detection node positions of all pipelines, and the target pressure data corresponding to the target pressure detection node position is used to obtain the pressure risk assessment coefficient, and the pressure control judgment of the pressure detection node position is performed using the pressure risk assessment coefficient.

6. The AI-based production safety control method according to claim 5 is characterized in that: When the pressure data of the pipeline exceeds the corresponding pressure risk threshold, a target pressure detection node position is selected from the pressure detection node positions of all pipelines, and a pressure risk evaluation coefficient is obtained using the target pressure data corresponding to the target pressure detection node position, and the pressure control determination of the pressure detection node position is performed using the pressure risk evaluation coefficient, including: When the pressure data of the pipeline exceeds the corresponding pressure risk threshold, the correlation coefficient between the pressure detection node position of the pipeline whose pressure data exceeds the corresponding pressure risk threshold and the pressure detection node positions of other pipelines is retrieved; Retrieving the pressure detection node positions of the pipelines whose pressure data exceeds the corresponding pressure risk threshold and the pressure detection node positions of other pipelines whose correlation coefficients exceed the preset correlation coefficient threshold as the target pressure detection node positions, and taking the pressure data corresponding to the target pressure detection node positions as the target pressure data; Obtaining a pressure risk assessment coefficient using the pressure data of the pipeline corresponding to the pressure detection node position of the pipeline where the pressure data of the pipeline exceeds the corresponding pressure risk threshold and its corresponding target pressure data; The pressure risk assessment coefficient is obtained by the following formula: Where K represents the pressure risk assessment coefficient; k represents the number of target pressure detection node locations; P g The pressure data of the pipeline corresponding to the pressure detection node position of the pipeline where the pressure data of the pipeline exceeds the corresponding pressure risk threshold; P gi represents the target pressure data corresponding to the position of the i-th target pressure detection node; F i represents the correlation coefficient between the pressure detection node position of the pipeline whose pressure data exceeds its corresponding pressure risk threshold and the i-th target pressure detection node position; δ represents the preset time attenuation coefficient; t i represents the total pressure data collection time corresponding to the i-th target pressure detection node position; λ 01 and λ 02 represent the first risk factor and the second risk factor respectively, and the first risk factor is obtained by the following formula: Among them, λ 01 represents the first risk factor; F i The correlation coefficient between the pressure detection node position of the pipeline whose pressure data exceeds its corresponding pressure risk threshold and the i-th target pressure detection node position; F y Indicates the preset correlation coefficient threshold; F max Indicates the maximum value of the correlation coefficient between the pressure detection node positions of the pipeline corresponding to the n target pressure detection node positions and the pressure data of the pipeline exceeding the corresponding pressure risk threshold; Furthermore, the second risk factor is obtained by the following formula: Among them, λ 02 represents the second risk factor; P gb The standard deviation of the pressure data corresponding to the pressure detection node position of the pipeline where the pressure data of the pipeline exceeds the corresponding pressure risk threshold; P gbi represents the standard deviation of the pressure data corresponding to the position of the i-th target pressure detection node; F i The correlation coefficient between the pressure detection node position of the pipeline indicating that the pressure data of the pipeline exceeds the corresponding pressure risk threshold and the i-th target pressure detection node position; Comparing the stress risk assessment coefficient with a preset stress risk assessment threshold; When the pressure risk assessment coefficient exceeds the preset pressure risk assessment threshold, the pipeline valve corresponding to the pressure detection node position of the pipeline whose pressure data exceeds its corresponding pressure warning threshold is adjusted to reduce the pressure value corresponding to the pressure detection node position of the pipeline.

7. The AI-based production safety control method according to claim 1 is characterized in that: The vibration operating parameters of each production equipment are collected in real time through the sensor group, and the equipment operation is safely regulated according to the vibration operating parameters of each production equipment, including: The vibration operation parameters of each production equipment are collected in real time by a sensor group, wherein the sensor group includes an acceleration sensor, a velocity sensor and a displacement sensor, and the vibration operation parameters include vibration acceleration, vibration velocity and vibration displacement generated by vibration; The vibration acceleration, vibration velocity and vibration displacement generated by the vibration of each production equipment are compared with the corresponding acceleration threshold, velocity threshold and vibration displacement threshold respectively; When any one of the vibration acceleration, vibration velocity and vibration displacement generated by the vibration exceeds its corresponding threshold, it is determined whether the production equipment needs to be safely regulated; When it is determined that safety regulation of the production equipment is required, the production equipment is decelerated and regulated.

8. The AI-based production safety control method according to claim 7 is characterized in that: When any one of the vibration acceleration, vibration velocity and vibration displacement generated by the vibration exceeds its corresponding threshold, it is determined whether the production equipment needs to be safely regulated, including: When any one of the vibration acceleration, vibration velocity and vibration displacement generated by vibration exceeds its corresponding threshold value, the corresponding time when any one of the vibration acceleration, vibration velocity and vibration displacement generated by vibration exceeds its corresponding threshold value is used as the data retrieval time; From the moment of data retrieval, the vibration operation parameters of the production equipment are retrieved in real time; wherein the vibration operation parameters include vibration acceleration, vibration velocity and vibration displacement generated by vibration; Obtaining a vibration operation evaluation coefficient using the vibration operation parameters of the production equipment; The vibration operation evaluation coefficient is obtained by the following formula: Among them, U represents the vibration operation evaluation coefficient; A, V and D represent vibration acceleration, vibration velocity and vibration displacement caused by vibration respectively; RMS (A, V, D) represents the sum of the square root values ​​of vibration acceleration, vibration velocity and vibration displacement caused by vibration; MAD (A, V, D) represents the sum of the mean absolute deviation values ​​of vibration acceleration, vibration velocity and vibration displacement caused by vibration; STD (A, V, D) represents the sum of the standard deviations of vibration acceleration, vibration velocity and vibration displacement caused by vibration; Var (A, V, D) represents the sum of the variances of vibration acceleration, vibration velocity and vibration displacement caused by vibration; K b represents a preset basic adjustment coefficient, and the value range of the basic adjustment coefficient is 1.32-1.47; σ represents a preset scaling factor, and the value range of the scaling factor is 0.18-0.53; ε represents a preset minimum constant, which is used to prevent the denominator from being zero; comparing the vibration operation evaluation coefficient with a preset vibration operation evaluation coefficient threshold; When the vibration operation evaluation coefficient exceeds a preset vibration operation evaluation coefficient, it is determined that safety regulation of the production equipment is required.

9. The AI-based production safety control method according to claim 7 is characterized in that: When it is determined that the production equipment needs to be safely regulated, the production equipment is decelerated and regulated, including: When it is determined that production equipment needs to be safely regulated, the vibration operation evaluation coefficient is retrieved; The vibration operation evaluation coefficient is used to obtain a deceleration control ratio of the production equipment, and the production equipment is decelerated and controlled according to the deceleration control ratio of the production equipment; The deceleration control ratio of the production equipment is obtained by the following formula: Among them, B represents the deceleration control ratio of the production equipment; r represents the preset proportional adjustment coefficient, and the value range of the proportional adjustment coefficient is 0.27-0.34; U represents the vibration operation evaluation coefficient.

10. A safe production control system based on AI, characterized in that: The AI-based safe production control system includes: The AI-based safe production control system includes: The first adjustment module is used to collect the pressure data of the wellhead and the pipeline in real time through the pressure sensor, and adjust the pressure of the wellhead and the pipeline according to the deviation between the pressure data of the wellhead and the pipeline and the production requirement index; The first safety warning module is used to issue a safety warning when the deviation between the pressure data of the wellhead and the pipeline and the production requirement index still cannot meet the preset deviation requirement after the pressure of the wellhead and the pipeline is regulated; A second adjustment module is used to collect the vibration operation parameters of each production equipment in real time through a sensor group, and to safely regulate the operation of the equipment according to the vibration operation parameters of each production equipment; The second safety warning module is used to issue a safety warning to the production equipment whose vibration operation still cannot meet its corresponding vibration operation standard after each production equipment completes safety regulation.

Images